Image processing apparatus, method, and program

Abstract

An image processing apparatus includes a depth control signal generation unit generating a depth control signal controlling emphasis of the feel of each region of an input image based on the depth position of a subject in each region of the input image; a face skin region control signal generation unit generating a face skin region control signal controlling emphasis of the feel of each region in the input image based on the human face skin region in the input image; a person region control signal generation unit generating a person region control signal controlling emphasis of the feel of each region in the input image based on the region of the person in the input image; and a control signal synthesis unit synthesizing the depth control signal, the face skin region control signal, and the person region control signal to generate a control signal.

What is claimed is: 
     
       1. An image processing apparatus comprising:
 a control signal synthesis unit configured to synthesize a depth control signal controlling a degree of emphasis of a feel of a plurality of regions, including regions encompassing a face skin region and regions not encompassing the face skin region, of an input image based on a depth position of a subject in each region of the input image and a face skin region control signal controlling the degree of emphasis of the feel of the regions encompassing the face skin region and the feel of the regions not encompassing the face skin region in the input image based on the face skin region in the input image to generate a control signal; and 
 an image processing unit configured to separately adjust the feel of the regions encompassing the face skin region and the feel of the regions not encompassing the face skin region of the input image, based on the control signal, to create a difference of perceived visual depth between a face of the subject in the input image that comprise the regions encompassing the face skin region, and the regions not encompassing the face skin region of the input image and that are outside of the face of the subject in the input image, 
 wherein the image processing unit comprises a prediction coefficient selection unit configured to select a prediction coefficient used in generation of an output image based on the control signal for each region of the output image, and a prediction calculation unit configured to generate the output image with a higher resolution than the input image based on the input image and the prediction coefficient, and 
 wherein the control signal synthesis unit and the image processing unit are each implemented via at least one processor. 
 
     
     
       2. The image processing apparatus according to  claim 1 , wherein the image processing unit is further configured to amplify or attenuate edge components of the input image based on the control signal. 
     
     
       3. The image processing apparatus according to  claim 1 , wherein the image processing unit is further configured to amplify a texture component of the input image based on the control signal. 
     
     
       4. The image processing apparatus according to  claim 3 , wherein the image processing unit is further configured to amplify or attenuate edge components of the input image based on a control signal other than the control signal. 
     
     
       5. The image processing apparatus according to  claim 1 , wherein the image processing unit is further configured to amplify or attenuate a chroma component of the input image, based on the control signal. 
     
     
       6. The image processing apparatus according to  claim 1 ,
 wherein the control signal synthesis unit is further configured to synthesize the depth control signal, the face skin region control signal, and a person region control signal controlling the degree of emphasis of a feel of each region in the input image based on a region of a person in the input image. 
 
     
     
       7. The image processing apparatus according to  claim 1 , wherein the control signal synthesis unit is further configured to synthesize the depth control signal, the face skin region control signal, and an interest region control signal controlling the degree of emphasis of a feel of each region in the input image based on a region estimated to be of high interest in the input image to generate the control signal. 
     
     
       8. The image processing apparatus according to  claim 1 , wherein the control signal synthesis unit is further configured to synthesize both the depth control signal and the face skin region control signal, to generate the control signal. 
     
     
       9. The image processing apparatus according to  claim 1 , wherein the control signal synthesis unit is further configured to weight the depth control signal and the face skin region control signal to generate the control signal. 
     
     
       10. The image processing apparatus according to  claim 1 , wherein the control signal synthesis unit is further configured to add the depth control signal and the face skin region control signal to generate the control signal. 
     
     
       11. An image processing method comprising:
 synthesizing a depth control signal controlling a degree of emphasis of a feel of a plurality of regions, including regions encompassing a face skin region and regions not encompassing the face skin region, of an input image based on a depth position of a subject in each region of the input image and a face skin region control signal controlling the degree of emphasis of the feel of the regions encompassing the face skin region and the feel of the regions not encompassing the face skin region in the input image based on the face skin region in the input image to generate a control signal; 
 adjusting, separately, the feel of the regions encompassing the face skin region and the feel of the regions not encompassing the face skin region of the input image based on the control signal, to create a difference of perceived visual depth between a face of the subject in the input image that comprise the regions encompassing the face skin region, and the regions not encompassing the face skin region of the input image and that are outside of the face of the subject in the input image; 
 selecting a prediction coefficient used in generation of an output image based on the control signal for each region of the output image; and 
 generating the output image with a higher resolution than the input image based on the input image and the prediction coefficient. 
 
     
     
       12. The image processing method according to  claim 11 , wherein edge components of the input image are amplified or attenuated based on the control signal. 
     
     
       13. The image processing method according to  claim 11 , wherein a texture component of the input image is amplified based on the control signal. 
     
     
       14. The image processing method according to  claim 13 , wherein edge components of the input image are amplified or attenuated based on another control signal other than the control signal. 
     
     
       15. The image processing method according to  claim 11 , wherein a chroma component of the input image is amplified or attenuated based on the control signal. 
     
     
       16. The image processing method according to  claim 11 , wherein the depth control signal, the face skin region control signal, and a person region control signal controlling the degree of emphasis of a feel of each region in the input image are synthesized based on a region of a person in the input image. 
     
     
       17. The image processing method according to  claim 11 , wherein the depth control signal, the face skin region control signal, and an interest region control signal controlling the degree of emphasis of a feel of each region in the input image are synthesized based on a region estimated to be of high interest in the input image to generate the control signal. 
     
     
       18. The image processing method according to  claim 11 , wherein the control signal synthesis unit is further configured to synthesize both the depth control signal and the face skin region control signal, to generate the control signal. 
     
     
       19. A non-transitory computer-readable medium having embodied thereon a program, which when executed by a computer causes the computer to perform an image processing method, the method comprising:
 synthesizing a depth control signal controlling a degree of emphasis of a feel of a plurality of regions, including regions encompassing a face skin region and regions not encompassing the face skin region, of an input image based on a depth position of a subject in each region of the input image and a face skin region control signal controlling the degree of emphasis of the feel of the region encompassing the face skin region and the feel of the regions not encompassing the face skin region in the input image based on the face skin region in the input image to generate a control signal; 
 adjusting, separately, the feel of the regions encompassing the face skin region and the feel of the regions not encompassing the face skin region of the input image based on the control signal, to create a difference of perceived visual depth between a face of the subject in the input image that comprise the regions encompassing the face skin region, and the regions not encompassing the face skin region of the input image and that are outside of the face of the subject in the input image; 
 selecting a prediction coefficient used in generation of an output image based on the control signal for each region of the output image; and 
 generating the output image with a higher resolution than the input image based on the input image and the prediction coefficient.